elaichi-clients

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables an AI agent to interface with third-party platforms (Slack, Jira, HubSpot) via the Elaichi MCP endpoint. This creates an attack surface for indirect prompt injection, where data retrieved from these sources could contain instructions designed to manipulate the agent.
  • Ingestion points: Data returned through the execute_tool command from connected external applications as described in SKILL.md.
  • Boundary markers: None identified. The instructions do not specify delimiters or directions for the agent to ignore embedded instructions in external data.
  • Capability inventory: The skill provides interaction capabilities via search_tools and execute_tool as well as organization data access in SKILL.md and references/per-client-setup.md.
  • Sanitization: No explicit data sanitization or validation steps are outlined for tool outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:58 PM
Security Audit — agent-trust-hub — elaichi-clients